Python numpy.nanquantile() Examples

def _process_symmetric(self, symmetric, clim, check_symmetric_max):
        if symmetric is not None or clim is not None:
            return symmetric

        if is_xarray(self.data):
            # chunks mean it's lazily loaded; nanquantile will eagerly load
            if self.data.chunks:
                return False
            data = self.data[self.z]
            if is_xarray_dataarray(data):
                if data.size > check_symmetric_max:
                    return False
            else:
                return False

        elif self._color_dim:
            data = self.data[self._color_dim]
        else:
            return

        cmin = np.nanquantile(data, 0.05)
        cmax = np.nanquantile(data, 0.95)

        return bool(cmin < 0 and cmax > 0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_nanquantile(self):
        self.check(np.nanquantile, 0.5)
        o = np.nanquantile(self.q, 50 * u.percent)
        expected = np.nanquantile(self.q.value, 0.5) * u.m
        assert np.all(o == expected) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def test_regression(self):
        ar = np.arange(24).reshape(2, 3, 4).astype(float)
        ar[0][1] = np.nan

        assert_equal(np.nanquantile(ar, q=0.5), np.nanpercentile(ar, q=50))
        assert_equal(np.nanquantile(ar, q=0.5, axis=0),
                     np.nanpercentile(ar, q=50, axis=0))
        assert_equal(np.nanquantile(ar, q=0.5, axis=1),
                     np.nanpercentile(ar, q=50, axis=1))
        assert_equal(np.nanquantile(ar, q=[0.5], axis=1),
                     np.nanpercentile(ar, q=[50], axis=1))
        assert_equal(np.nanquantile(ar, q=[0.25, 0.5, 0.75], axis=1),
                     np.nanpercentile(ar, q=[25, 50, 75], axis=1)) 

def test_no_p_overwrite(self):
        # this is worth retesting, because quantile does not make a copy
        p0 = np.array([0, 0.75, 0.25, 0.5, 1.0])
        p = p0.copy()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0)

        p0 = p0.tolist()
        p = p.tolist()
        np.nanquantile(np.arange(100.), p, interpolation="midpoint")
        assert_array_equal(p, p0) 

def test_basic(self):
        x = np.arange(8) * 0.5
        assert_equal(np.nanquantile(x, 0), 0.)
        assert_equal(np.nanquantile(x, 1), 3.5)
        assert_equal(np.nanquantile(x, 0.5), 1.75) 

def fit(self, X, y=None):
        """
        Computes the quantiles for each column of ``X``.

        :type X: pandas.DataFrame or numpy.ndarray
        :param X: The column(s) from which the capping limit(s) will be computed.

        :param y: Ignored.

        :rtype: sklego.preprocessing.ColumnCapper
        :returns: The fitted object.

        :raises:
            ``ValueError`` if ``X`` contains non-numeric columns
        """
        X = check_array(
            X, copy=True, force_all_finite=False, dtype=FLOAT_DTYPES, estimator=self
        )

        # If X contains infs, we need to replace them by nans before computing quantiles
        np.putmask(X, (X == np.inf) | (X == -np.inf), np.nan)

        # There should be no column containing only nan cells at this point. If that's not the case,
        # it means that the user asked ColumnCapper to fit some column containing only nan or inf cells.
        nans_mask = np.isnan(X)
        invalid_columns_mask = (
            nans_mask.sum(axis=0) == X.shape[0]
        )  # Contains as many nans as rows
        if invalid_columns_mask.any():
            raise ValueError(
                "ColumnCapper cannot fit columns containing only inf/nan values"
            )

        q = [quantile_limit / 100 for quantile_limit in self.quantile_range]
        self.quantiles_ = np.nanquantile(
            a=X, q=q, axis=0, overwrite_input=True, interpolation=self.interpolation
        )

        # Saving the number of columns to ensure coherence between fit and transform inputs
        self.n_columns_ = X.shape[1]

        return self 

def map_cdf(
    x: xr.DataArray,
    y: xr.DataArray,
    y_value: xr.DataArray,
    *,
    group: Union[str, Grouper] = "time",
    skipna: bool = False,
):
    """Return the value in `x` with the same CDF as `y_value` in `y`.

    Parameters
    ----------
    x : xr.DataArray
      Values from which to pick
    y : xr.DataArray
      Reference values giving the ranking
    y_value : float, array
      Value within the support of `y`.
    dim : str
      Dimension along which to compute quantile.

    Returns
    -------
    array
      Quantile of `x` with the same CDF as `y_value` in `y`.
    """

    def _map_cdf_1d(x, y, y_value, skipna=False):
        q = _ecdf_1d(y, y_value)
        _func = np.nanquantile if skipna else np.quantile
        return _func(x, q=q)

    def _map_cdf_group(gr, y_value, dim=["time"], skipna=False):
        return xr.apply_ufunc(
            _map_cdf_1d,
            gr.x,
            gr.y,
            input_core_dims=[dim] * 2,
            output_core_dims=[["x"]],
            vectorize=True,
            keep_attrs=True,
            kwargs={"y_value": y_value, "skipna": skipna},
            dask="parallelized",
            output_dtypes=[gr.x.dtype],
        )

    return group.apply(
        _map_cdf_group, {"x": x, "y": y}, y_value=np.atleast_1d(y_value), skipna=skipna,
    ) 

def main(args=None):
    """
    Main function to generate the polarization plot.
    """
    args = parse_arguments().parse_args(args)

    pc1 = pd.read_table(args.pca, header=None, sep="\t",
                        dtype={0: "object", 1: "Int64", 2: "Int64", 3: "float32"})

    pc1 = pc1.rename(columns={0: "chr", 1: "start", 2: "end", 3: "pc1"})

    if args.outliers != 0:
        quantile = [args.outliers / 100, (100 - args.outliers) / 100]
        boundaries = np.nanquantile(pc1['pc1'].values.astype(float), quantile)
        quantiled_bins = np.linspace(boundaries[0], boundaries[1],
                                     args.quantile)
    else:
        quantile = [j / (args.quantile - 1) for j in range(0, args.quantile)]
        quantiled_bins = np.nanquantile(pc1['pc1'].values.astype(float),
                                        quantile)

    pc1["quantile"] = np.searchsorted(quantiled_bins,
                                      pc1['pc1'].values.astype(float),
                                      side="right")
    pc1.loc[pc1["pc1"] == np.nan]["quantile"] = args.quantile + 1
    polarization_ratio = []
    output_matrices = []
    labels = []
    for matrix in args.obsexp_matrices:
        obs_exp = hm.hiCMatrix(matrix)
        name = ".".join(matrix.split("/")[-1].split(".")[0:-1])
        labels.append(name)
        normalised_sum_per_quantile = count_interactions(obs_exp, pc1,
                                                         args.quantile,
                                                         args.offset)
        normalised_sum_per_quantile = np.nan_to_num(normalised_sum_per_quantile)
        if args.outputMatrix:
            output_matrices.append(normalised_sum_per_quantile)

        polarization_ratio.append(within_vs_between_compartments(
                                  normalised_sum_per_quantile,
                                  args.quantile))
    if args.outputMatrix:
        np.savez(args.outputMatrix, [matrix for matrix in output_matrices])
    plot_polarization_ratio(
        polarization_ratio, args.outputFileName, labels, args.quantile)